CN206441536U - A kind of active voice assistant based on recognition of face - Google Patents
A kind of active voice assistant based on recognition of face Download PDFInfo
- Publication number
- CN206441536U CN206441536U CN201621109953.2U CN201621109953U CN206441536U CN 206441536 U CN206441536 U CN 206441536U CN 201621109953 U CN201621109953 U CN 201621109953U CN 206441536 U CN206441536 U CN 206441536U
- Authority
- CN
- China
- Prior art keywords
- control module
- cloud server
- central control
- face
- external equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Abstract
The utility model is related to a kind of active voice assistant based on recognition of face, the voice assistant includes external equipment, cloud server and central control module, the central control module is connected with external equipment and cloud server respectively, the external equipment includes camera and microphone, and the camera and microphone are mounted on being connected on car and with central control module.Compared with prior art, the utility model has the advantages that interactive performance is strong, drive safety is high, strong using simple and compatible extensions.
Description
Technical field
The utility model is related to field of face identification, more particularly, to a kind of active voice assistant based on recognition of face.
Background technology
With the popularization of automobile consumption, comfort level when people drive to automobile product requires more and more higher.Full Vehicle System
Increasing amusement function is added, causes the hidden danger of some driving safeties.The introducing of voice assistant is delayed to a certain extent
Solve such case, and then the automobile industry in today becomes more and more popular.Driver only needs to say related voice instruction, so that it may
To manipulate vehicle device, it is to avoid sight deviates road ahead or the distractive potential safety hazard such as manually operated.
But, the voice assistant on current market is all passivity.Voice assistant can keep silent for a long time, it is necessary to
Driver says that special instruction goes to wake up it.Its behavior is more like an instruction interpreter, rather than a voice assistant, because
Its degree of understanding to driver is very low, and such voice assistant, which is scarcely out of swaddling-clothes, many aspects to be hoisted.
Utility model content
The purpose of this utility model is to provide a kind of active voice assistant based on recognition of face regarding to the issue above.
The purpose of this utility model can be achieved through the following technical solutions：
A kind of active voice assistant based on recognition of face, the voice assistant include external equipment, cloud server and
Central control module, the central control module is connected with external equipment and cloud server respectively, and the external equipment includes
Camera and microphone, the camera and microphone are mounted on being connected on car and with central control module.
The external equipment also includes loudspeaker, and the loudspeaker is respectively mounted to be connected with car and with central control module.
The cloud server includes face recognition chip and voice recognition chip, and the face recognition chip and voice are known
Other chip is connected with central control module.
The central control module includes signal transmission unit and controller, and the signal transmission unit is set with external respectively
Standby and cloud server connection, the controller is connected with signal transmission unit.
The signal transmission unit include signal receiver and wave filter, the signal receiver respectively with cloud server
With wave filter connection, the wave filter is connected with controller.
Compared with prior art, the utility model has the advantages that：
(1) face recognition chip is provided with cloud server, face recognition can be carried out to driver, and according to face knowledge
Other result actively initiates the interaction with driver, and Active Performance is high.
(2) voice recognition chip is provided with cloud server, the phonetic order of driver can be analyzed and carried out
Feedback, is combined with face recognition, improves the interactive performance of whole voice assistant.
(3) what user can be sent by microphone to voice assistant, which actively instruct, answers, and greatly simplifies driver
Output order complexity.
(4) face recognition chip is compared with traditional face identification device, in addition to it can recognize the identity of driver, can be with
Facial expression to driver is caught, and is then analyzed the state of attention and emotional state of driver, is noted in driver
Power is not concentrated or reminds driver in time during fatigue driving, improves the security of driving.
Brief description of the drawings
Fig. 1 is structural representation of the present utility model；
Fig. 2 is the corresponding schematic diagram of face recognition information and instruction action；
Wherein, 1 is central control module, and 2 be cloud server, and 3 be loudspeaker, and 4 be camera, and 5 be microphone.
Embodiment
The utility model is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with the utility model
Implemented premised on technical scheme, give detailed embodiment and specific operating process, but guarantor of the present utility model
Shield scope is not limited to following embodiments.
As shown in figure 1, be the active voice assistant based on recognition of face, including：External equipment, for gathering driver's
Face recognition signal and voice signal, while carrying out relevant action according to operational order；Cloud server 2, for analyzing face
Signal is recognized, the state of driver is judged, and analyzes voice signal, the instruction that driver sends is judged；Central control module 1,
For the face recognition signal and transmission of sound signals that collect external equipment to cloud server 2, and according to cloud service
The analysis result of device 2 sends operational order to external equipment.
Wherein, external equipment includes：Signal collecting device, the face recognition signal harmony message for gathering driver
Number, and transmit to central control module 1；Loudspeaker 3, for carrying out relevant action according to the operational order of central control module 1.
Signal collecting device includes：Camera 4, for gathering the face recognition signal of driver and transmitting to central control module 1；Wheat
Gram wind 5, for gathering the voice signal of driver and transmitting to central control module 1.
Cloud server 2 includes：Face recognition chip, for analyzing face recognition signal, judges the state of driver, and
It will determine that result is sent to central control module 1；Voice recognition chip, for analyzing voice signal, judges what driver sent
Instruction, and will determine that result is sent to central control module 1.
Central control module 1 includes：Signal transmission unit, for receive face recognition signal that external device collects and
Voice signal, and transmit to cloud server 2；Main control unit, for the analysis result fed back according to cloud server 2, sends
Operational order is to external equipment.
Above-mentioned voice assistant operationally, by camera 4 (the present embodiment uses high-resolution camera) collection, know by face
Central control unit, then the face recognition chip being transferred on cloud server 2, recognition of face core are connected to after other vision signal
Analysis result is fed back into central control unit after piece signal Analysis, central control unit connection loudspeaker 3 sends " hello " and referred to
Order, user sends control instruction by microphone 5, finally connects vehicular amusement apparatus and completes control, and in particular to the work arrived
Principle is as follows：
High-resolution camera can catch the countenance information for collecting driver, such as current drivers be male or
Women, expression is pleasure or gloomy.Central control module 1 can get video flowing from high-resolution camera module, in
Control module 1 is entreated by the recognition of face core of (or card is locally stored) on the video stream got to cloud server 2
Piece is parsed；Face recognition chip analyzes the facial information of driver in the video flowing sended over, and then feedback result is arrived
Central control unit；The controlling loudspeaker 3 of central control module 1 says " hello " instruction to driver, according to the result recognized
Information provides some of the recommendations or warning, such as recognizes the expression of joy, play some easily music；What is recognized is four
The middle-aged male of ten years old or so can provide the service of some finance and economics, and recognize young woman when when can provide current popular
Still information service, specific corresponding to relation are as shown in Fig. 2 such as after voice assistant provides the instruction of " broadcasting song ", user
Microphone 5 is fed back to, the instruction similar to " song for playing Liu De China " is said, then central control module 1 receives user and referred to
Parsing carries out the operation of next step after order；Identification correspond to user's greeting；Age/gender identification correspond to a variety of ages/
The instruction action of sex service；Expression Recognition correspond to play relaxed music, the command operating such as tell funny stories.
Claims (1)
1. a kind of active voice assistant based on recognition of face, the voice assistant include external equipment, cloud server and in
Control module is entreated, the central control module is connected with external equipment and cloud server respectively, it is characterised in that described external
Equipment includes camera, microphone and loudspeaker, and the camera, microphone and loudspeaker are mounted on car and controlled with center
Molding block is connected；The cloud server includes face recognition chip and voice recognition chip, the face recognition chip and language
Sound identification chip is connected with central control module；The central control module includes signal transmission unit and controller, described
Signal transmission unit is connected with external equipment and cloud server respectively, and the controller is connected with signal transmission unit；It is described
Signal transmission unit includes signal receiver and wave filter, and the signal receiver connects with cloud server and wave filter respectively
Connect, the wave filter is connected with controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621109953.2U CN206441536U (en) | 2016-10-10 | 2016-10-10 | A kind of active voice assistant based on recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621109953.2U CN206441536U (en) | 2016-10-10 | 2016-10-10 | A kind of active voice assistant based on recognition of face |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206441536U true CN206441536U (en) | 2017-08-25 |
Family
ID=59644446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201621109953.2U Expired - Fee Related CN206441536U (en) | 2016-10-10 | 2016-10-10 | A kind of active voice assistant based on recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206441536U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109935228A (en) * | 2017-12-15 | 2019-06-25 | 富泰华工业（深圳）有限公司 | Identity information interconnected system and method, computer storage medium and user equipment |
-
2016
- 2016-10-10 CN CN201621109953.2U patent/CN206441536U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109935228A (en) * | 2017-12-15 | 2019-06-25 | 富泰华工业（深圳）有限公司 | Identity information interconnected system and method, computer storage medium and user equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107919117A (en) | A kind of active voice assistant based on recognition of face | |
| CN203861914U (en) | Pet robot | |
| CN108831460A (en) | A kind of interactive voice control system and method based on fatigue monitoring | |
| CN107657950B (en) | Automobile voice control method, system and device based on cloud and multi-command words | |
| CN103730119A (en) | Vehicle-mounted man-machine voice interaction system | |
| CN204870729U (en) | Vehicle information interaction controlling means | |
| CN203607093U (en) | A cloud-and-terminal-based vehicle-mounted man-machine voice interaction system | |
| CN111968642A (en) | Voice data processing method and device and intelligent vehicle | |
| CN108274974A (en) | A kind of speech control system and method for on-board air conditioner | |
| CN208675495U (en) | The playback equipment that vehicle and its multimedia automatically control | |
| CN106550286A (en) | Based on the real-time intercommunication method under driving environment, terminal, server and system | |
| CN101645716B (en) | Vehicle-borne communication system having voice recognition function and recognition method thereof | |
| CN206441536U (en) | A kind of active voice assistant based on recognition of face | |
| CN111833875A (en) | Embedded voice interaction system | |
| CN105137895A (en) | Internal environment monitoring and voice control system for passenger car | |
| CN112562267A (en) | Vehicle-mounted safety robot and safe driving assistance method | |
| CN204926573U (en) | Intelligent robot of auxiliary exercise mandarin | |
| CN104930642B (en) | One kind realizes interactive air conditioner and its method of work based on voice | |
| CN109545215A (en) | A kind of awakening method and Rouser of vehicle intelligent equipment | |
| CN111477224A (en) | Human-vehicle virtual interaction system | |
| CN106094673A (en) | Automobile wakes up word system and control method thereof up | |
| CN109448714A (en) | The method that voice Rouser, robot and voice wake up | |
| CN210760611U (en) | Man-machine interaction system based on artificial intelligence | |
| CN205395785U (en) | Adopt speech synthesis mode to carry out audio alert's CAN bus instrument | |
| CN209285962U (en) | A kind of sound control starting device of electric wheelchair |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 215126 No. 123 Changyang street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee after: Annex Electronics (Suzhou) Co., Ltd. Address before: 215126 No. 123 Changyang street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee before: Delphi Electronics (Suzhou) Co., Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170825 Termination date: 20201010 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |